[CVPR 2025] Official PyTorch implementation of "EdgeTAM: On-Device Track Anything Model"

MapAnything: Universal Feed-Forward Metric 3D Reconstruction

ViPE: Video Pose Engine for Geometric 3D Perception

Official code for "No time to train! Training-Free Reference-Based Instance Segmentation"

The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained model checkpoints, and example notebooks that show how to use th…

Official Implementation of paper "MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motion"

[CVPR 2025 Best Paper Award Candidate] VGGT: Visual Geometry Grounded Transformer

Official implementation of On-the-fly Reconstruction for Large-Scale Novel View Synthesis from Unposed Images. A. Meuleman, I. Shah, A. Lanvin, B. Kerbl, G. Drettakis, ACM TOG (proc. SIGGRAPH) 2025

[CVPR 2025 Best Paper Nomination] FoundationStereo: Zero-Shot Stereo Matching

[CVPR 2025] MASt3R-SLAM: Real-Time Dense SLAM with 3D Reconstruction Priors

Grounding Image Matching in 3D with MASt3R

Gaga: Group Any Gaussians via 3D-aware Memory Bank

[CVPR 2025] Sparse Voxels Rasterization: Real-time High-fidelity Radiance Field Rendering

Official implementation of the SIGGRAPH 2024 paper "A Hierarchical 3D Gaussian Representation for Real-Time Rendering of Very Large Datasets"

3D Reconstruction with Spatial Memory

Depth Pro: Sharp Monocular Metric Depth in Less Than a Second.

VGGSfM: Visual Geometry Grounded Deep Structure From Motion

InstantSplat: Sparse-view SfM-free Gaussian Splatting in Seconds

[Arxiv 2023] RoMa: Revisiting Robust Losses for Dense Feature Matching

Deep Patch Visual Odometry

Codebase for the WayveScenes101 Dataset

The repo for "Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Image"

CONSAC: Robust Multi-Model Fitting by Conditional Sample Consensus